© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97685
    Prev
    Next
    INDEX
    Explanations

    government/organizations/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Congress
    -0.83
     Parliament
    -0.65
     Council
    -0.62
    Congress
    -0.58
    Council
    -0.54
     CONGRESS
    -0.52
    ThroughAttribute
    -0.51
     COUNCIL
    -0.51
    ful
    -0.50
    Personendaten
    -0.47
    POSITIVE LOGITS
    ſelf
    0.82
     myſelf
    0.81
     itſelf
    0.80
    bibfield
    0.78
     purpoſe
    0.77
     houſe
    0.75
     ſtate
    0.74
    daß
    0.73
    neſs
    0.71
     himſelf
    0.71
    Activations Density 0.185%

    No Known Activations